powernode-platform CLAUDE.md

Project instructions for Powernode, an open-source control plane for managing AI-agent fleets. They describe its Rails API, React frontend, Sidekiq worker, extensions, database, and rules for locating development guidance.

In plain words
What is it for?
Use them when working on Powernode's backend, frontend, worker, extensions, governance, agent coordination, or infrastructure and lifecycle features.
Why use it?
They give an agent the system layout and identify which instructions are always required versus recalled from other sources. This reduces the risk of changing the wrong service or ignoring project conventions.

Instructions file

Install

Getting it into your agent

One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.

agentmods
npx agentmods add instructions/nodealchemy/powernode-platform/claude-md
Clone the repo
git clone --depth 1 https://github.com/nodealchemy/powernode-platform
Per session 3,514 This file is loaded in full into every session.
When invoked 3,514 The same file — it is already loaded in full.
Security scan A 0 findings. Scan, not verified.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5 $0.03514 $0.03514
Opus 5 $0.01757 $0.01757
Sonnet 5 $0.00703 $0.00703
Haiku 4.5 $0.00351 $0.00351

Measured yesterday against content hash 7798f085dc4b, method: parsed. Prices are Anthropic first-party input rates as of 2026-08-30, from the pricing page.

Security

Grade A, and why

powernode-platform CLAUDE.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

CLAUDE.md · 173 lines

How it starts

The opening of the file, as written. The whole thing — 173 lines — stays where its author put it; the contents beside it link to each section on GitHub.

CLAUDE.md

Development guidance for Powernode: open-source mission control for AI agent fleets. This file is the outage-safe core — only global, high-stakes rules that must hold even if the MCP server is down. Situational rules live in hooks, scripts/pattern-validation.sh, and docs/contributing/conventions/ (recalled MCP-first). See Where guidance lives.

Project Overview

Control plane for production AI agent fleets — knowledge graph, governance, swarm coordination, MCP-native runtime, and the fleet substrate (bare-metal / VM / container lifecycle). MIT.

  • Backend: Rails 8 API (./server) — JWT auth, UUIDv7 PKs. Does NOT run Sidekiq.
  • Frontend: React TypeScript (./frontend) — theme-aware, Tailwind.
  • Worker: Sidekiq standalone (./worker) — API-only communication.
  • Public extensions (git submodules, MIT on GitHub): ./extensions/system, ./extensions/marketing, ./extensions/supply-chain.
  • Private extensions (remote-only, not in public clones; added by maintainers): under ./extensions/private/*. The platform runs in core mode when absent — single-user self-hosted, all core capabilities unlocked, no billing/SaaS.
  • Database: PostgreSQL (native UUID) + pgvector.

Project Status: docs/reference/auto/todo.md (auto-generated — do not edit).

Core Models

Account → User (many), Agent (many), Skill (many)
User → Roles, Permissions, Invitations
Agent → Conversations, Tasks, Goals, ApprovalRequests

Where guidance lives

Rules are routed by trigger shape — the mechanism that surfaces or enforces each one when relevant:

Rule shape Home Surfaces / enforces via
Always + high-stakes + not checkable this file (core) always loaded
Mechanically checkable .claude/hooks/*.sh + scripts/pattern-validation.sh edit-time hook / adherence scan
Reusable pattern / procedure conventions/ + platform knowledge MCP-first queries + SessionStart digest
Subsystem-scoped nested server//frontend//worker/ CLAUDE.md loads when editing that tree
Decision / incident / preference auto-memory (~/.claude/.../memory/MEMORY.md) harness relevance injection
Crypto / private-extension logic extension only (never core) core-purity-check.sh (blocking)

Read the full file on GitHub · 173 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. yesterday First seen · 173 lines · 3,514 tokens per session scan A 7798f085dc4b

Subscribe to this mod's changes

powernode-platform CLAUDE.md is an instructions file published in the GitHub repository nodealchemy/powernode-platform (2 stars, last pushed 3d ago), licensed MIT. It adds 3,514 tokens to every session, about $0.0176 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.